Adversarially Trained Actor Critic for Offline Reinforcement Learning.
Ching-An ChengTengyang XieNan JiangAlekh AgarwalPublished in: ICML (2022)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- approximate dynamic programming
- optimal control
- reinforcement learning algorithms
- neuro fuzzy
- gradient method
- function approximation
- state space
- policy iteration
- model free
- policy gradient methods
- markov decision processes
- dynamic programming
- learning problems
- control problems
- rl algorithms
- training set
- machine learning
- supervised learning
- learning algorithm
- natural actor critic
- step size
- markov decision process
- transfer learning
- reinforcement learning methods